4 papers
TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
Mengyao Du, Han Fang, Haokai Ma +4
Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit…
Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier
Mengyao Du, Gang Yang, Han Fang +2
The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate w…
NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models
Fang Yuan, Junjie Zeng, Yue Hu +3
SOAR, a classic symbol-based cognitive architecture, has been fostering the development of general, human-like intelligent agents. Nevertheless, its practical adoption is hindered…
Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events
Mengzhu Liu, Zhengqiu Zhu, Chuan Ai +8
During sudden disaster events, accurately predicting public panic sentiment on social media is crucial for proactive governance and crisis management. Current efforts on this probl…